Despite much research targeted at enabling conventional machine learning models to continually learn tasks and data distributions sequentially without forgetting the knowledge acquired, little effort has been devoted to account for more realistic situations where learning some tasks accurately might be more critical than forgetting previous ones. In this paper we propose a Bayesian inference based framework to continually learn a set of real-world, sensing-based analysis tasks that can be tuned to prioritize the remembering of previously learned tasks or the learning of new ones. Our experiments prove the robustness and reliability of the learned models to adapt to the changing sensing environment, and show the suitability of using uncertainty of the predictions to assess their reliability.
翻译:尽管进行了许多研究,目的是使传统机器学习模式能够连续不断地学习任务和数据分配,同时不忘获得的知识,但很少努力去考虑更现实的情况,在这些情况下,准确学习某些任务可能比忘记以前的任务更为关键。在本文件中,我们提议了一个基于贝叶斯推论的框架,以不断学习一套现实世界的、基于遥感的分析工作,这些任务可以调整为对过去学到的任务或新任务进行优先的记忆或学习。我们的实验证明,为适应不断变化的遥感环境而学习的模型是健全和可靠的,并表明利用预测的不确定性评估其可靠性是适当的。